公开(公告)号：US20210065019A1

公开(公告)日：2021-03-04

申请号：US16554233

申请日：2019-08-28

申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

发明人： Oznur ALKAN ,  Adi BOTEA ,  Akihiro KISHIMOTO ,  Radu MARINESCU ,  Biplav SRIVASTAVA

IPC分类号： G06N5/04 ,  G06N5/02 ,  G06N20/00 ,  G06F16/24

摘要： Various embodiments are provided for applying judgment reasoning knowledge in a dialog system in a computing environment by a processor. A determination is made that a response to a query during a dialog using the dialog system fails to comply with one or more expected response patterns to one of a plurality of query responses. An updated response may be provided to the query using judgment reasoning knowledge for matching the updated response with the one or more expected response patterns.

公开(公告)号：US20190278792A1

公开(公告)日：2019-09-12

申请号：US16421807

申请日：2019-05-24

申请人： International Business Machines Corporation

发明人： Murray S. Campbell ,  MIAO LIU ,  Biplav SRIVASTAVA

IPC分类号： G06F16/332 ,  G06F17/27 ,  G06F3/16 ,  G10L15/18 ,  G10L15/06 ,  G06F16/9032 ,  G06F16/242 ,  G10L15/22

摘要： Embodiments of the present invention provide a system for implementing multi-turn dialogs. The system performs a method that includes receiving a series of user utterances, generating a series of responsive system utterances, and labeling the series of responsive system utterances to generate training data for training a dialog management policy. The labeling includes executing a reward function at each turn of a dialog, in which for each turn of the dialog the reward function is configured to output a reward value that is based at least in part on an accuracy of the responsive system utterance of the turn and on number of dialog turns elapsed.

公开(公告)号：US20160019102A1

公开(公告)日：2016-01-21

申请号：US14331892

申请日：2014-07-15

申请人： International Business Machines Corporation

发明人： Jie CUI ,  Florian PINEL ,  Biplav SRIVASTAVA ,  Xin ZHOU

IPC分类号： G06F9/54 ,  G06F11/30 ,  G06F11/34

CPC分类号： G06F9/542 ,  G06F8/36 ,  G06F8/74 ,  G06F11/302 ,  G06F11/3409 ,  G06F11/3466 ,  G06F17/40 ,  G06F2201/865

摘要： API associations among a plurality of service application programming interfaces may be identified by analyzing service API call logs, which contain data associated with invocation of the plurality of application programming interfaces by a plurality of applications, wherein sets of APIs that are determined to be called together are identified. For a set of service APIs, a plurality of applications that invoke the APIs in the set is identified. A sequence of API calls by an application in the plurality of applications is identified, wherein multiples sequences of APIs are identified, one sequence of API calls identified respectively for one application in the plurality of applications. An application pattern is determined based on the multiple sequences of service APIs.

摘要翻译： 可以通过分析服务API调用日志来识别多个服务应用程序编程接口中的API关联，其包含与多个应用程序调用多个应用程序编程接口相关联的数据，其中确定要一起调用的API集合 被识别。 对于一组服务API，识别了在该集合中调用API的多个应用程序。 识别由多个应用中的应用程序进行的API调用序列，其中识别多个API序列，分别为多个应用中的一个应用识别出一个API调用序列。 基于服务API的多个序列来确定应用模式。

公开(公告)号：US20200012954A1

公开(公告)日：2020-01-09

申请号：US16028136

申请日：2018-07-05

申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

发明人： Adi I. BOTEA ,  Oznur ALKAN ,  Elizabeth DALY ,  Matthew DAVIS ,  Akihiro KISHIMOTO ,  Vera LIAO ,  Radu MARINESCU ,  Biplav SRIVASTAVA ,  Kartik TALAMADUPULA ,  Yunfeng ZHANG

IPC分类号： G06N5/04 ,  G10L15/06

摘要： Various embodiments are provided for integrating multiple domain learning and personalization in a dialog system for a user in a computing environment by a processor. One or more problem instances may be defined for multiple domains according to a problem instance template, identified user intent, links to one or more problem solvers associated with the multiple domains, or a combination thereof. A dialog plan may be determined to further define the one or more problem instances in response to user input. A solution may be provided to the user for the one or more problem instances.

公开(公告)号：US20180285770A1

公开(公告)日：2018-10-04

申请号：US15475551

申请日：2017-03-31

申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

发明人： Lydia MANIKONDA ,  Shirin SOHRABI ARAGHI ,  Biplav SRIVASTAVA ,  Kartik TALAMADUPULA

IPC分类号： G06N99/00 ,  G06N7/00

摘要： Embodiments for learning personalized actionable domain models by a processor. A domain model may be generated according to a plurality of actions, extracted from one or more online data sources, of a plurality of cluster representatives. The plurality of actions achieve a goal. A hierarchical action model may be generated based on probabilities of the domain model and the plurality of actions. The hierarchical action model comprises a sequence of actions of the plurality of actions for achieving the goal. The hierarchical action model may be personalized by filtering to a selected set of actions according to weighted actions of the plurality of actions.